The choice of the most suitable activation functions for artificial neural networks significantly affects training time and task performance. Breast cancer detection is currently based on the use of neural networks and their selection is an element that affects performance. In the present work, reference information on activation functions in neural networks was analyzed. Exploratory research, comprehensive reading, stepwise approach, and deduction were applied as a method. It resulted in phases of comparative evaluation inactivation functions, a quantitative and qualitative comparison of activation functions, and a prototype of neural network algorithm with activation function to detect cancer; It was concluded that the final results put as the best option to use ReLU for early detection of cancer.
|Title of host publication
|Human Interaction, Emerging Technologies and Future Systems V - Proceedings of the 5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and the 6th IHIET
|Subtitle of host publication
|Future Systems IHIET-FS 2021
|Tareq Ahram, Redha Taiar
|Springer Science and Business Media Deutschland GmbH
|Number of pages
|Published - 2022
|5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and 6th International Conference on Human Interaction and Emerging Technologies: Future Systems, IHIET-FS 2021 - Virtual, Online
Duration: 27 Aug 2021 → 29 Aug 2021
|Lecture Notes in Networks and Systems
|5th International Virtual Conference on Human Interaction and Emerging Technologies, IHIET 2021 and 6th International Conference on Human Interaction and Emerging Technologies: Future Systems, IHIET-FS 2021
|27/08/21 → 29/08/21
Bibliographical noteFunding Information:
This work has been supported by the GIIAR research group and the Universidad Polit?cnica Salesiana.
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
- Activation functions
- Cancer detection
- Neural networks